Student Performance Prediction Using Technology of Machine Learning

In the given paper, the main focus of this report is education. Student performance prediction is our main target. Various factors have been taken into account to create a model used for student performance prediction. This helps to analyze the student’s study environment so that his success rate increases in the field of studies. Our project makes use of various effective machine learning algorithms for creating the predictive model. Mainly, it is based on linear regression, decision trees, Naïve Bayes classification, K-nearest neighbors (KNN), and some improvements carried out through feature engineering that modifies the data to make it easier in understanding for ML. Data sets containing students’ information are arranged in a tabular format. The row represents the name of the student, while each column contains different details about the student such as his background of the family, sex, any information about medical reports, and age. An additional column contains the variable of success rate that the algorithm is trying to predict. The final report is evaluated through these algorithms in which a function outputs whether the student can be successful or not. “Feat Hunch–Student Performance Predictor in ML” aims at connecting all the students and teachers in an institute.